John Deere is using Intel's artificial intelligence technology to solve costly problems in the manufacturing welding process for its manufacturing facilities by piloting a solution that uses computer vision to automatically identify common defects in automated welding processes.

"Welding is a complicated process, and this AI solution has the potential to help us produce our high-quality machines more efficiently than before," said Andy Benko, quality director, John Deere Construction & Forestry Division. "The introduction of new technology into manufacturing is opening up new opportunities and changing the way we think about some processes that haven't changed in years," he added.

Why is Intel's technology being used by John Deere?

John Deere uses the Gas Metal Arc Welding process to weld steel at 52 of its global factories, where hundreds of robotic arms create machines and products.

Porosity, defined as cavities in the weld metal caused by trapped gas bubbles as it cools, is a common welding challenge, according to John Deere.

If these flaws are discovered late in the manufacturing process, the products will need to be reworked or scrapped, which can be time-consuming and costly for manufacturers.

For John Deere, traditional methods for detecting GMAW defects have been a manual process requiring highly skilled technicians.

John Deere is collaborating with Intel to address weld porosity in an effort to find solutions to issues that arise with this volume of welding.

The partnership brings two of John Deere's core values together: innovation and quality.

"We wanted to push technology to make John Deere's weld quality better than it's ever been because that's our commitment to our customers and what they expect from John Deere," Benko continued.

With their collaboration, the two will pool their resources to create an integrated, end-to-end system of hardware and software that can generate real-time insights at the edge.

Intel and John Deere's solution uses a neural network-based inference engine to log defects in real time and automatically stop the welding process.

John Deere can now correct issues in real time and produce high-quality products thanks to the solution.

"By leveraging Intel technology and smart infrastructure in their factories, Deere is positioning themselves well to capitalize not only on this welding solution, but potentially others that emerge as part of their broader Industry 4.0 transformation," concluded Christine Boles, vice president in Intel's Insight division.

Read the original article "In manufacturing welding, John Deere uses Intel's AI | AI & Automation | Manufacturing Global" at